Spatial Memory Intelligence: Endowing World Models with Understanding-Driven Long-Term Memory Paper • 2610.02521 • Published 14 days ago • 60
DataFlex-RL: An Evaluation Platform for RLVR Data Policies Paper • 2609.06107 • Published Sep 5 • 168
Beyond the Stability-Exploration Dilemma: Environmental Regularization for LLM Policy Optimization Paper • 2608.23311 • Published Aug 24 • 17
OmniAssistBench: Assistant-style Interaction Benchmark for Omni-LLMs Paper • 2608.21360 • Published Aug 21 • 32
Light-Omni: Reflex over Reasoning in Agentic Video Understanding with Long-Term Memory Paper • 2607.05511 • Published Jul 6 • 24
EvoEmbedding: Evolvable Representations for Long-Context Retrieval and Agentic Memory Paper • 2606.21649 • Published Jun 19 • 36
UniPrefill: Universal Long-Context Prefill Acceleration via Block-wise Dynamic Sparsification Paper • 2605.06221 • Published May 7 • 21
Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding Paper • 2604.05015 • Published Apr 6 • 233
VideoDetective: Clue Hunting via both Extrinsic Query and Intrinsic Relevance for Long Video Understanding Paper • 2603.22285 • Published Mar 23 • 50
Omni-Diffusion: Unified Multimodal Understanding and Generation with Masked Discrete Diffusion Paper • 2603.06577 • Published Mar 6 • 50
VITA-E: Natural Embodied Interaction with Concurrent Seeing, Hearing, Speaking, and Acting Paper • 2510.21817 • Published Oct 21, 2025 • 41